EP 3983941 A4 20230517 - SCALABLE THREE-DIMENSIONAL OBJECT RECOGNITION IN A CROSS REALITY SYSTEM
Title (en)
SCALABLE THREE-DIMENSIONAL OBJECT RECOGNITION IN A CROSS REALITY SYSTEM
Title (de)
SKALIERBARE DREIDIMENSIONALE OBJEKTERKENNUNG IN EINEM REALITÄTSÜBERGREIFENDEN SYSTEM
Title (fr)
RECONNAISSANCE D'OBJET TRIDIMENSIONNEL ÉVOLUTIVE DANS UN SYSTÈME DE RÉALITÉ TRANSVERSAL
Publication
Application
Priority
- US 201962861784 P 20190614
- US 202062968023 P 20200130
- US 202063006408 P 20200407
- US 202063024291 P 20200513
- US 2020037573 W 20200612
Abstract (en)
[origin: US2020394848A1] Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for scalable three-dimensional (3-D) object recognition in a cross reality system. One of the methods includes maintaining object data specifying objects that have been recognized in a scene. A stream of input images of the scene is received, including a stream of color images and a stream of depth images. A color image is provided as input to an object recognition system. A recognition output that identifies a respective object mask for each object in the color image is received. A synchronization system determines a corresponding depth image for the color image. A 3-D bounding box generation system determines a respective 3-D bounding box for each object that has been recognized in the color image. Data specifying one or more 3-D bounding boxes is received as output from the 3-D bounding box generation system.
IPC 8 full level
G06T 7/11 (2017.01); G06T 7/73 (2017.01); G06V 10/764 (2022.01); G06V 20/00 (2022.01)
CPC (source: EP US)
G06T 7/11 (2017.01 - EP US); G06T 7/50 (2017.01 - US); G06T 7/73 (2017.01 - EP); G06T 19/20 (2013.01 - US); G06V 10/764 (2022.01 - EP US); G06V 20/00 (2022.01 - EP US); G06T 2207/10016 (2013.01 - EP); G06T 2207/10024 (2013.01 - EP US); G06T 2207/10028 (2013.01 - EP US); G06T 2207/20084 (2013.01 - EP US)
Citation (search report)
- [I] CHARLES R QI ET AL: "Frustum PointNets for 3D Object Detection from RGB-D Data", PROCEEDINGS OF THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION(CVPR), IEEE, 13 April 2018 (2018-04-13), pages 918 - 927, XP033476053, DOI: 10.1109/CVPR.2018.00102
- [A] JI HOU ET AL: "3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 17 December 2018 (2018-12-17), XP081200201
- [A] LAHOUD JEAN ET AL: "2D-Driven 3D Object Detection in RGB-D Images", 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), IEEE, 22 October 2017 (2017-10-22), pages 4632 - 4640, XP033283338, DOI: 10.1109/ICCV.2017.495
- See also references of WO 2020252371A1
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
DOCDB simple family (publication)
US 11257300 B2 20220222; US 2020394848 A1 20201217; CN 114730498 A 20220708; EP 3983941 A1 20220420; EP 3983941 A4 20230517; JP 2022537810 A 20220830; JP 2024012657 A 20240130; JP 7448566 B2 20240312; US 11704806 B2 20230718; US 2022139057 A1 20220505; WO 2020252371 A1 20201217
DOCDB simple family (application)
US 202016899878 A 20200612; CN 202080057105 A 20200612; EP 20822482 A 20200612; JP 2021574263 A 20200612; JP 2023196666 A 20231120; US 2020037573 W 20200612; US 202217574305 A 20220112